{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/mixed-segmentation","entry":"mixed_segmentation","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":5,"n_papers_ran":3,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":3,"n_samples_ran":1,"n_samples_fingerprinted":1,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"unverified":2},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2303.12528","paper":"/paper/mega-multilingual-evaluation-of-generative-ai","title":"MEGA: Multilingual Evaluation of Generative AI","date":"2023-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/Multilingual-Evaluation-of-Generative-AI-MEGA","path":"mega/compile_qa_results.py","file_url":"https://github.com/microsoft/Multilingual-Evaluation-of-Generative-AI-MEGA/blob/HEAD/mega/compile_qa_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"21d4edd99200edf1","mcp_get_code":{"code_sha256":"21d4edd99200edf1"}},{"arxiv_id":"2004.13922","paper":"/paper/revisiting-pre-trained-models-for-chinese","title":"Revisiting Pre-Trained Models for Chinese Natural Language Processing","date":"2020-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ymcui/Chinese-ELECTRA","path":"cmrc2018_drcd_evaluate.py","file_url":"https://github.com/ymcui/Chinese-ELECTRA/blob/HEAD/cmrc2018_drcd_evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2ac9d5179c0b5c85","mcp_get_code":{"code_sha256":"2ac9d5179c0b5c85"}},{"arxiv_id":"1910.07475","paper":"/paper/mlqa-evaluating-cross-lingual-extractive","title":"MLQA: Evaluating Cross-lingual Extractive Question Answering","date":"2019-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/MLQA","path":"mlqa_evaluation_v1.py","file_url":"https://github.com/facebookresearch/MLQA/blob/HEAD/mlqa_evaluation_v1.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"b6a95b947b35a4d6","mcp_get_code":{"code_sha256":"b6a95b947b35a4d6"}},{"arxiv_id":"2023.emnlp-main.803","paper":null,"title":"arXiv:2023.emnlp-main.803","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"yisunlp/Anti-CF","path":"utils/mlqa_evaluate.py","file_url":"https://github.com/yisunlp/Anti-CF/blob/HEAD/utils/mlqa_evaluate.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b6a95b947b35a4d6","mcp_get_code":{"code_sha256":"b6a95b947b35a4d6"}},{"arxiv_id":"2021.acl-long.48","paper":null,"title":"arXiv:2021.acl-long.48","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"PluviophileYU/COSY","path":"XQA/src/mlqa_evaluation_v1.py","file_url":"https://github.com/PluviophileYU/COSY/blob/HEAD/XQA/src/mlqa_evaluation_v1.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b6a95b947b35a4d6","mcp_get_code":{"code_sha256":"b6a95b947b35a4d6"}}]}